English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Using multimodal Magnetic Resonance Imaging (MRI) is necessary for accuratebrain tumor segmentation. The main problem is that not all types of MRIs arealways available in clinical exams. Based on the fact that there is a strongcorrelation between MR modalities of the same patient, in this work, we proposea novel brain tumor segmentation network in the case of missing one or moremodalities. The proposed network consists of three sub-networks: afeature-enhanced generator, a correlation constraint block and a segmentationnetwork. The feature-enhanced generator utilizes the available modalities togenerate 3D feature-enhanced image representing the missing modality. Thecorrelation constraint block can exploit the multi-source correlation betweenthe modalities and also constrain the generator to synthesize afeature-enhanced modality which must have a coherent correlation with theavailable modalities. The segmentation network is a multi-encoder based U-Netto achieve the final brain tumor segmentation. The proposed method is evaluatedon BraTS 2018 dataset. Experimental results demonstrate the effectiveness ofthe proposed method which achieves the average Dice Score of 82.9, 74.9 and59.1 on whole tumor, tumor core and enhancing tumor, respectively across allthe situations, and outperforms the best method by 3.5%, 17% and 18.2%.

Feature-enhanced Generation and Multi-modality Fusion based Deep Neural Network for Brain Tumor Segmentation with Missing MR Modalities